collaborators

7 papers

cs.CV2026

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models

Arnas Uselis, Andrea Dittadi, Seong Joon Oh

Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems. Although modern models are trained on massiv…

cs.CV2026

When Do Diffusion Models learn to Generate Multiple Objects?

Yujin Jeong, Arnas Uselis, Iro Laina +2

Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, th…

cs.CV2026

How can embedding models bind concepts?

Arnas Uselis, Darina Koishigarina, Seong Joon Oh

Humans easily determine which color belongs to which shape in multi-object scenes, an ability known as concept binding. Vision-language embedding models such as CLIP struggle with…

cs.CV2026

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models

Fabian Morelli, Arnas Uselis, Ankit Sonthalia +1

Large-scale pre-trained vision-language models like CLIP demonstrate remarkable zero-shot performance across diverse tasks. However, fine-tuning these models to improve downstream…

cs.CV2026

Half-Truths Break Similarity-Based Retrieval

Bora Kargi, Arnas Uselis, Seong Joon Oh

When a text description is extended with an additional detail, image-text similarity should drop if that detail is wrong. We show that CLIP-style dual encoders often violate this i…

cs.CV2026

Enhancing Multi-Image Understanding through Delimiter Token Scaling

Minyoung Lee, Yeji Park, Dongjun Hwang +3

Large Vision-Language Models (LVLMs) achieve strong performance on single-image tasks, but their performance declines when multiple images are provided as input. One major reason i…